{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5EHUC7Q2U63TJG5ERYQURL3KQG","short_pith_number":"pith:5EHUC7Q2","schema_version":"1.0","canonical_sha256":"e90f417e1aa7b7349ba48e2148af6a818d57be97c0e5541ffe33dc96f21f6e61","source":{"kind":"arxiv","id":"2312.00600","version":2},"attestation_state":"computed","paper":{"title":"Improving Plasticity in Online Continual Learning via Collaborative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ling Xiao, Maorong Wang, Nicolas Michel, Toshihiko Yamasaki","submitted_at":"2023-12-01T14:06:28Z","abstract_excerpt":"Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL, the training data can only be seen once. Most existing online CL research regards catastrophic forgetting (i.e., model stability) as almost the only challenge. In this paper, we argue that the model's capability to acquire new knowledge (i.e., model plasticity) is another challenge in online CL. While replay-based strategies have been shown to be effective in alleviating catastrophic forgetting, there is a notable "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.00600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-01T14:06:28Z","cross_cats_sorted":[],"title_canon_sha256":"78b32b0a98fd15f5d0ecbe8e8f886a23d8941ecc819a3bb4f1e156f878bfba6d","abstract_canon_sha256":"2f69314ba46f13593b44c624bfb6fe373067c13e6daf5ee3f59e0c71b3b31562"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:48.798763Z","signature_b64":"Fd9oRUm1gfeHylXF4yOfVGWZ/6R3yd+KN2uGWKLbCy1pEeDd4ZX3bKL1yQLyA3N81uhUtP9gq8uk7SsCE6xqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e90f417e1aa7b7349ba48e2148af6a818d57be97c0e5541ffe33dc96f21f6e61","last_reissued_at":"2026-07-05T08:02:48.798280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:48.798280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Plasticity in Online Continual Learning via Collaborative Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ling Xiao, Maorong Wang, Nicolas Michel, Toshihiko Yamasaki","submitted_at":"2023-12-01T14:06:28Z","abstract_excerpt":"Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL, the training data can only be seen once. Most existing online CL research regards catastrophic forgetting (i.e., model stability) as almost the only challenge. In this paper, we argue that the model's capability to acquire new knowledge (i.e., model plasticity) is another challenge in online CL. While replay-based strategies have been shown to be effective in alleviating catastrophic forgetting, there is a notable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00600","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.00600/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.00600","created_at":"2026-07-05T08:02:48.798343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00600v2","created_at":"2026-07-05T08:02:48.798343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00600","created_at":"2026-07-05T08:02:48.798343+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EHUC7Q2U63T","created_at":"2026-07-05T08:02:48.798343+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EHUC7Q2U63TJG5E","created_at":"2026-07-05T08:02:48.798343+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EHUC7Q2","created_at":"2026-07-05T08:02:48.798343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13852","citing_title":"Dealing with Synthetic Data Contamination in Online Continual Learning","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG","json":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG.json","graph_json":"https://pith.science/api/pith-number/5EHUC7Q2U63TJG5ERYQURL3KQG/graph.json","events_json":"https://pith.science/api/pith-number/5EHUC7Q2U63TJG5ERYQURL3KQG/events.json","paper":"https://pith.science/paper/5EHUC7Q2"},"agent_actions":{"view_html":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG","download_json":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG.json","view_paper":"https://pith.science/paper/5EHUC7Q2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00600&json=true","fetch_graph":"https://pith.science/api/pith-number/5EHUC7Q2U63TJG5ERYQURL3KQG/graph.json","fetch_events":"https://pith.science/api/pith-number/5EHUC7Q2U63TJG5ERYQURL3KQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG/action/storage_attestation","attest_author":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG/action/author_attestation","sign_citation":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG/action/citation_signature","submit_replication":"https://pith.science/pith/5EHUC7Q2U63TJG5ERYQURL3KQG/action/replication_record"}},"created_at":"2026-07-05T08:02:48.798343+00:00","updated_at":"2026-07-05T08:02:48.798343+00:00"}